Truncate or Not? A Scaling Study of Looped Transformers with Truncated Backpropagation
Measures how forward loop counts and truncated backpropagation affect language-model pretraining across model sizes and data budgets. Fits scaling laws to compare full backpropagation through fewer loops with truncated alternatives at matched compute.
First public: · Added to this list: October 22, 2026
Explore this approach
Recurrent reasoning — Repeat parts of the model or keep intermediate information in memory while working through a problem. Some methods also learn how many passes to run.
Analysis and evaluation — Measure how well these methods work, investigate what their internal computation does, and identify where they fail. This includes experiments, studies of model internals, and mathematical results.